Breno Livio Silva de Almeida

Contact

Breno Livio Silva de Almeida
PhD student

Working Group Microbial Data Science

Department of Computational Biology and Chemistry
Helmholtz Centre for Environmental Research - UFZ
Permoserstr. 15, 04318 Leipzig, Germany

Phone +55 11 96839 2259
breno.almeida@ufz.de

Breno Livio Silva de Almeida

Scientific Career

07/2024 present

PhD student - Double-degree in Computer Science between University of Sao Paulo (USP, Sao Paulo, Brazil) and University of Leipzig (Leipzig, Germany).

01/2020 02/2024

BSC Degree - BSc Degree in Computer Science - Special Studies in Data Science and Data Engineering at the University of São Paulo


Research interests

Since high school, when I built a simple chatbot to aid interventions for autistic individuals, I have been passionate about using computer science for social good. In college, my interest in biology and nutrition led me to explore, through machine learning and bioinformatics, the links between complex disorders and the human gut microbiome. Since 2021, I have continued this mission by applying democratizing tools like AutoML, enabling non-experts to leverage machine learning.

My current research focuses on alignment-free machine learning methods to analyze biological sequences that are too divergent for traditional annotation. By using language models to capture evolutionary and ecological signals in proteins, I aim to uncover novel enzymes that could advance medicine, industry, and sustainability. In simple terms, I am working to reveal the “functional dark matter” of proteins, the vast number whose roles are unknown because current comparison methods cannot detect their distant evolutionary links. Just as language models find patterns in human language, they can read the “language of life” to unlock nature’s untapped potential.

Publications

  • Duan, Y., Santos-Júnior, C. D., Schmidt, T. S., Fullam, A., de Almeida, B. L., Zhu, C., ... & Coelho, L. P. (2024). A catalog of small proteins from the global microbiome. Nature Communications, 15(1), 7563.
  • Avila Santos, A. P., de Almeida, B. L., Bonidia, R. P., Stadler, P. F., Stefanic, P., Mandic-Mulec, I., ... & de Carvalho, A. C. (2024). BioDeepfuse: a hybrid deep learning approach with integrated feature extraction techniques for enhanced non-coding RNA classification. RNA biology, 21(1), 410-421.
  • Bonidia, R. P., Avila Santos, A. P., de Almeida, B. L., Stadler, P. F., Nunes da Rocha, U., Sanches, D. S., & De Carvalho, A. C. (2022). Information theory for biological sequence classification: A novel feature extraction technique based on tsallis entropy. Entropy, 24(10), 1398.
  • Bonidia, R. P., Santos, A. P. A., de Almeida, B. L., Stadler, P. F., da Rocha, U. N., Sanches, D. S., & de Carvalho, A. C. (2022). BioAutoML: automated feature engineering and metalearning to predict noncoding RNAs in bacteria. Briefings in Bioinformatics, 23(4), bbac218.
  • de Almeida, B. L. S., Queiroz, A. P., Santos, A. P. A., Bonidia, R. P., da Rocha, U. N., Sanches, D. S., & de Carvalho, A. C. P. D. L. F. (2021, November). Feature importance analysis of non-coding dna/rna sequences based on machine learning approaches. In Brazilian Symposium on Bioinformatics (pp. 81-92). Cham: Springer International Publishing.